INDEX

Explanations

programming-related terminology and functions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AllowAnonymous

-0.17

atori

-0.16

ilingual

-0.15

 Bang

-0.15

edir

-0.14

 Null

-0.14

phan

-0.14

vais

-0.14

ives

-0.14

irie

-0.14

POSITIVE LOGITS

 signed

0.25

overflow

0.25

 Overflow

0.24

 overflow

0.24

æº

0.24

Overflow

0.23

signed

0.21

Signed

0.21

_overflow

0.21

 Signed

0.20

Activations Density 0.053%

programming-related terminology and functions

No Comments

No Known Activations